Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add emiliaprotocol/emilia-protocolnpx agentmods add plugins/emiliaprotocol/emilia-protocol/claude-code-plugingit clone --depth 1 https://github.com/emiliaprotocol/emilia-protocolGrade A, and why
claude-code-plugin scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "emilia-guard",
"description": "Require a named human's signed approval before Claude does anything irreversible — money movement, destructive shell, external sends. High-risk tool calls are held until a person approves on their own device (Face ID / passkey), producing an offline-verifiable Trust Receipt. Fail-closed.",
"version": "0.1.0",
"author": { "name": "EMILIA Protocol", "url": "https://www.emiliaprotocol.ai" },
"homepage": "https://www.emiliaprotocol.ai",
"repository": "https://github.com/emiliaprotocol/emilia-protocol",
"license": "Apache-2.0",
"keywords": ["security", "human-in-the-loop", "approval", "agent-safety", "irreversible-actions", "webauthn", "audit"],
"mcpServers": {
"emilia": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@emilia-protocol/mcp-server"],
"env": {
"EP_BASE_URL": "https://www.emiliaprotocol.ai",
"EP_API_KEY": "${EP_API_KEY}"
}
}
}
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 22 lines scan A 688104127966
claude-code-plugin is a plugin published in the GitHub repository emiliaprotocol/emilia-protocol (653 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
trustshell
Plugin marketplace listing 1 plugin: trustshell.
trustshell
AI agent security for Claude Code — read the code, break the running agent, prove it (exploit-validated). Commands: /static-scan, /red-team. Subagent: agent-red-teamer. Skills: RT-1..RT-9.
fedramp-ssp
Convert FedRAMP Rev 5 Moderate SSP DOCX templates to validated OSCAL 1.2.0 JSON. Wraps ethanolivertroy/frdocx-to-froscal-ssp — ready for oscal-cli, Compliance Trestle, eMASS, and FedRAMP 20X workflows.
palas-plugins-official
Directorio de plugins de Palas: herramientas de productividad y habilidades especializadas para PYMEs.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.